Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1863 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3346. Min Act: -0.0000

Data Index: 91501 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.9486. Min Act: -0.0000

Data Index: 313065 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.0512. Min Act: -0.0000

Data Index: 958203 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.0406. Min Act: -0.0000

Data Index: 668913 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.8324. Min Act: -0.0000

Data Index: 169413 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.6858. Min Act: -0.0000

Data Index: 931626 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.6586. Min Act: -0.0000

Data Index: 547004 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.5655. Min Act: -0.0000

Data Index: 781751 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.5693. Min Act: -0.0000

Data Index: 905067 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.5637. Min Act: -0.0000

Data Index: 703701 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.4293. Min Act: -0.0000

Data Index: 241114 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.5671. Min Act: -0.0000

Data Index: 335514 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.6735. Min Act: -0.0000

Data Index: 1229236 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.5401. Min Act: -0.0000

Data Index: 70374 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.3886. Min Act: -0.0000

Data Index: 727171 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.5076. Min Act: -0.0000

Data Index: 112863 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.6260. Min Act: -0.0000

Data Index: 75095 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.6002. Min Act: -0.0000

Data Index: 1317874 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.4527. Min Act: -0.0000

Data Index: 90627 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.3232. Min Act: -0.0000

Data Index: 1210751 (C4 (Web Text))

Max Activating Token Index: 811